Kevin M. Wade

Degrees

BAgrSc, MAgrSc (Dublin)
PhD (Cornell)

Short Bio

Kevin Wade was born in Ireland, educated in Agricultural Sciences (BSc, MSc) at University College Dublin, and obtained his PhD in Animal Breeding and Genetics from Cornell University (1990). Following a post-doctoral fellowship at the University of Guelph, where he implemented national genetic evaluations for Calving Ease in Dairy cattle, he was hired in McGill’s Department of Animal Science to fill the NSERC-Semex position in Dairy Information Systems (1992). Wade leads a group of researchers dedicated to the improvement of dairy-herd management through the exploitation of collected data. This principally involves collaboration with Valacta – the Dairy Production Centre of Expertise for Quebec and Atlantic Canada. In addition to leading this research group, Wade has served at various levels of administration at McGill – University Senate, Director of Continuing Professional Development (AES), and Chair of the Department of Animal Science from (2007 – 2018). He is a past Chair of the Macdonald Campus Committee on Information Technologies, and represents the Faculty on the University Teaching and Learning Services Committee. As the Faculty's Dairy Academic Lead, Wade continues to spearhead, and be involved in, large-scale research initiatives in dairy-production research, teaching, and infrastructure.

Professional activities

• Director, Dairy Information Systems Group
• Member, Ordre des agronomes du Québec
  • Comité de formation continue
  • Comité des équivalences
• Board member (McGill Representative), Valacta
• Board member (McGill Representative), CRSAD
• Participant, Dairy Brain
• Collaborating Member, Op+Lait
• Member, GRESABO

Research interests

Research in Applied Artificial Intelligence: various applications (artificial neural networks; case-based reasoning; decision-tree analyses; etc.) have been used in the development of prediction tools for milk production and incidence of disease in dairy cattle.

Big Data Analyses: through the use of data mining and the investigation of cube database technologies, the large amounts of milk-recording data are being examined with a view to discovering potential relationships among easily-recorded data and traits of economic interest.

On-farm Management Systems: the development of dairy-cattle lifetime models, helped by advances in data visualization, is allowing producers and advisors to better understand the profitability aspects of their enterprises through the identification of outliers and the impact of poor management decisions.

Current Research

• Use of machine learning to determine the effect of forage quality on milk production in dairy cattle.
• The effect of heifer growth on early-life fertility in dairy cattle.
• Use of Knowledge Graphs for predictive analyses
• Information from robotic milking systems

Courses

Publications

To view a list of current publications, please click here.